检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Xu, Xiangyu Zheng, Zhi Wang, Jin Chen, Yikai Huang, Jingyang Wu, Ruixin Yu, Huan Lu, Guodong The State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310058 China Zhejiang Key Laboratory of Industrial Big Data and Robot Intelligent Systems Zhejiang University Hangzhou310058 China Robotics Research Center of Yuyao City Ningbo315400 China College of Control Science and Engineering Zhejiang University Hangzhou310027 China

Flapping-wing robots offer great versatility;however, achieving efficient multi-modal locomotion remains challenging. This paper presents the design, modeling, and experimentation of T3, a novel tailless flapping-wing robot with three pairs of independently actuated wings. Inspired by juvenile water striders, T3 incorporates bio-inspired elastic passive legs that effectively transmit vibrations generated during wing flapping, enabling ground movement without additional motors. This novel mechanism facilitates efficient multi-modal locomotion while minimizing actuator usage, reducing complexity, and enhancing performance. An SE(3)-based controller ensures precise trajectory tracking and seamless mode transition. To validate T3’s effectiveness, we developed a fully functional prototype and conducted targeted modeling, real-world experiments, and benchmark comparisons. The results demonstrate the robot’s and controller’s outstanding performance, underscoring the potential of multi-modal flapping-wing technologies for future aerial-ground robotic applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Antenna grounds

来源：评论

学校读者我要写书评

暂无评论

SIM: A Scenario IMagination Based Deep Reinforcement Learning Method for Outdoor Transportation Environment Exploration 11

SIM: A Scenario IMagination Based Deep Reinforcement Learnin...

引用

11th IEEE Data Driven control and Learning systems Conference, DDCLS 2022

作者： Li, Haoran Zhang, Qichao Chen, Yaran Zhao, Dongbin State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518000 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

Autonomous exploration is very important for robotics, especially for mapping, navigation, and planning in an unknown environment. In recent years, automatic exploration methods in the indoor environment have been extensively studied, but there is little research on exploration in the outdoor transportation environment. Due to the limitations of outdoor traffic rules and the scale of the environment, the methods for the indoor environment are difficult to apply to the transportation environment. Aiming at exploration in the transportation environment, this paper proposes a deep reinforcement learning algorithm based on Scenario IMagination(SIM), which has two important components: 1) a mid-level action space, which combines the classical robot control algorithm, addressing the inefficient learning and unstable navigation of deep reinforcement learning algorithms in automatic exploration. With this action space, the deep reinforcement learning algorithm achieves excellent exploration performance in both normal scale environments and large-scale branchless environments;2) a scenarios buffer, which relieves hard exploration problems of deep reinforcement learning due to serious imbalances of samples in large-scale multibranch scenarios. Compared to the map-less navigation approaches, SIM achieves excellent exploration performance in large-scale multi-branch environments. © 2022 IEEE.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Research on master-slave teleoperation control algorithm based on exoskeleton master hand

Research on master-slave teleoperation control algorithm bas...

引用

第35届中国控制与决策会议

作者： Jing Hou Yong Jiang Liang Zhao Peng Yu Jinxiang Pian School of Electrical and control Engineering Shenyang Jianzhu University State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of Sciences

In order to obtain a more anthropomorphic experience in remote control,we use a wearable exoskeleton type master hand,which can obtain real-time human upper limb motion *** through the master-slave constraint algorithm,it completes the synchronous control of the slave robot,and then completes a series of tasks that people cannot directly participate *** original control scheme is further optimized,so that the tracking accuracy of the slave end effector is significantly ***,the Denavit-Hartenberg model of the master and slave devices is established through Robotic Toolbox 9.10 robot toolbox,and the workspace of the master and slave devices is analyzed respectively using Monte Carlo ***,the control scheme is designed to make the master exoskeleton complete the high-precision real-time control of the slave ***,the simulation results show that the master exoskeleton can complete the synchronization control of the slave robot,and the terminal accuracy is further improved on the basis of the original algorithm.

关键词： teleoperation exoskeleton master hand robot motion control positioning accuracy

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning Method to Estimate Bottomhole Pressure Dynamics of Oil Wells

Application of Deep Learning Method to Estimate Bottomhole P...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Haibo Cheng Shichao Li Peng Zeng Valeriy Vyatkin State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Department of Computer Science Electrical and Space Engineering Luleå University of Technology Luleå Sweden Department of Electrical Engineering and Automation Aalto University Helsinki Finland

Surrogate models, which have become an effective and popular method to close loop reservoir management problems, use a data-driven approach to predict dynamic injection and production wells parameters and optimize waterflooding development. In this study, a deep learning-based surrogate model method is proposed to estimate bottomhole pressure (BHP) of production wells in waterflooding reservoirs. Bidirectional long short-term memory (BiLSTM) network, as an efficient deep learning approach, is applied to BHP estimation using fluctuation data. Extended Fourier amplitude sensitivity test (EFAST) method is employed to analyse the influence of different input factors on BHP dynamics, and a reduced dataset is rebuilt to predict BHP parameter based on BiLSTM-EFAST algorithm. The estimation results are tested on a dataset from Volve oilfield in North Sea, and compared with other deep learning methods. The test results indicate that the proposed method can achieve higher prediction accuracy. A reduced dataset-based approach provides a new attempt to reduce model complexity and improve calculation speed for big data-driven surrogate model in oil and gas industry.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnostic Opportunities for Robot Servo Motors Using the Physics of Failure Analysis

Fault Diagnostic Opportunities for Robot Servo Motors Using ...

引用

International Conference on Reliability, Maintainability and Safety,ICRMS

作者： Bo Zhang Shan Liang Kai Wang Key Laboratory of Networked Control Systems Shenyang Institute of Automation Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China College of Computer Science and Technology University of Chemical Technology Chinese Academy of Sciences Shenyang China

ISBN: (数字)9798350329988

ISBN: (纸本)9798350329995

Joint robots are widely used in various industries, such as aviation, aerospace, and automotive manufacturing. The performance degradation of servo motors can significantly affect the overall performance of the robots because of the core component of joint robots, and therefore, it is critical to detect and address servo motor failures promptly. In this study, we analyze some common causes and mechanisms of performance degradation in robot servo motors using the physics of failure analysis. We also discuss strategies for detecting and diagnosing faults using these mechanisms before the servo motors fail completely.

关键词： Degradation Industries Service robots Failure analysis Safety Manufacturing Reliability Servomotors Physics Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

An optimization Strategy for Deep Neural Networks Training

An optimization Strategy for Deep Neural Networks Training

引用

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Tingting Wu Peng Zeng Chunhe Song State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665464697

Learning rate is one of the essential hyperparameters influencing the training process and the accuracy of deep neural networks. However, until now, it is challenging to determine an optimal learning rate. A large learning rate can accelerate the training process but may bring instability in the training process and miss the global optimum. In contrast, a small learning rate would be in a stable training process, but the training speed would be slow, and the training process is easy to fall into local optimum. In this paper, first, the impact of the learning rate is analyzed. It is found that a learning rate schedule should consist of two stages to take into account the speed and accuracy of the training process simultaneously. Based on this consideration, this paper proposes an improvement strategy of learning rate schedules: a two-stage integration strategy of a large fixed learning rate and a rapid decay learning rate. Second, the proposed strategy is applied to optimize a series of widely used learning rate settings. Extensive experiments on CIFAR-10 and CIFAR-100 datasets with VGG19, ResNets, ResNext, DenseNets, SeNet, and some other models demonstrate that the proposed strategy optimizes the learning rate settings, the performance of trained models is enhanced.

关键词： Training Deep learning Measurement Schedules Computational modeling Neural networks Predictive models

来源：评论

学校读者我要写书评

暂无评论

Based on an improved Zero-DCE++ low-light enhanced object detection algorithm

Based on an improved Zero-DCE++ low-light enhanced object de...

引用

2024 International Conference on Mechatronic Engineering and Artificial Intelligence, MEAI 2024

作者： Bai, Xuecheng Gao, Hongwei Zhao, Zhanpeng Yan, Zhiwen School of Automation and Electrical Engineering Shenyang Ligong University Liaoning Shenyang110159 China Institute of International Engineering Shenyang Ligong University Liaoning Shenyang110159 China China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Liaoning Shenyang110159 China Xi'an Modern Control Technology Research Institute Xi'an710100 China

ISBN: (纸本)9781510689176

Low-light image quality often suffers from noise, color distortion, and reduced contrast, challenging accurate object detection. Traditional enhancement methods can lead to over-processing and semantic information loss. This study presents an enhanced low-light image detection model based on an improved Zero-DCE++ algorithm, integrated with YOLOv8 for high-speed, accurate detection. key improvements include the CBAM attention mechanism to enhance feature extraction in low-light areas, DCNv2 for capturing complex object details, and a Local Region Brightness Curve Enhancement Module to prevent overexposure in well-lit areas. The proposed model was tested on the Night Drone dataset, where it achieved superior performance in image quality and detection accuracy compared to state-of-the-art methods. This approach demonstrates significant potential for applications requiring reliable object detection in challenging low-light conditions. © 2025 SPIE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Optimal control Formulation of Tool Affordance Applied to Impact Tasks

arXiv

引用

arXiv 2024年

作者： Ti, Boyang Gao, Yongsheng Zhao, Jie Calinon, Sylvain The State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin150001 China Idiap Research Institute MartignyCH-1920 Switzerland Lausanne1015 Switzerland

Humans use tools to complete impact-aware tasks such as hammering a nail or playing tennis. The postures adopted to use these tools can significantly influence the performance of these tasks, where the force or velocity of the hand holding a tool plays a crucial role. The underlying motion planning challenge consists of grabbing the tool in preparation for the use of this tool with an optimal body posture. Directional manipulability describes the dexterity of force and velocity in a joint configuration along a specific direction. In order to take directional manipulability and tool affordances into account, we apply an optimal control method combining iterative linear quadratic regulator (iLQR) with the alternating direction method of multipliers (ADMM). Our approach considers the notion of tool affordances to solve motion planning problems, by introducing a cost based on directional velocity manipulability. The proposed approach is applied to impact tasks in simulation and on a real 7-axis robot, specifically in a nail-hammering task with the assistance of a pilot hole. Our comparison study demonstrates the importance of maximizing directional manipulability in impact-aware tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Collision Avoidance Using Velocity Obstacle-Based control Barrier Functions

arXiv

引用

arXiv 2025年

作者： Huang, Jihao Zeng, Jun Chi, Xuemin Sreenath, Koushil Liu, Zhitao Su, Hongye State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Institute of Intelligence Science and Engineering Shenzhen Polytechnic University Shenzhen China Hybrid Robotics Group The Department of Mechanical Engineering UC Berkeley United States

Designing safety-critical controllers for acceleration-controlled unicycle robots is challenging, as control inputs may not appear in the constraints of control Lyapunov functions (CLFs) and control barrier functions (CBFs), leading to invalid controllers. Existing methods often rely on state-feedback-based CLFs and high-order CBFs (HOCBFs), which are computationally expensive to construct and fail to maintain effectiveness in dynamic environments with fast-moving, nearby obstacles. To address these challenges, we propose constructing velocity obstacle-based CBFs (VOCBFs) in the velocity space to enhance dynamic collision avoidance capabilities, instead of relying on distance-based CBFs that require the introduction of HOCBFs. Additionally, by extending VOCBFs using variants of VO, we enable reactive collision avoidance between robots. We formulate a safety-critical controller for acceleration-controlled unicycle robots as a mixed-integer quadratic programming (MIQP), integrating state-feedback-based CLFs for navigation and VOCBFs for collision avoidance. To enhance the efficiency of solving the MIQP, we split the MIQP into multiple sub-optimization problems and employ a decision network to reduce computational costs. Numerical simulations demonstrate that our approach effectively guides the robot to its target while avoiding collisions. Compared to HOCBFs, VOCBFs exhibit significantly improved dynamic obstacle avoidance performance, especially when obstacles are fast-moving and close to the robot. Furthermore, we extend our method to distributed multi-robot systems. Copyright © 2025, The Authors. All rights reserved.

关键词： state feedback

来源：评论

学校读者我要写书评

暂无评论

An Improved Dual Neural Network Method Based on Levy Flight for Multi-Robot Cooperative Area Coverage Search in 3D Unknown Environments

引用

IEEE Transactions on Cognitive and Developmental systems 2025年

作者： Zhang, Fangfang Wang, Yongqi Wang, Wenhao Xin, Jianbin Peng, Jinzhu Wang, Yaonan Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China State Key Laboratory of Intelligent Agricultural Power Equipment Luoyang471039 China National Engineering Laboratory of Robot Visual Perception and Control Technology School of Robotics Hunan University Changsha410082 China

The research on multi-robot collaborative search in unknown 3D environments, based on bio-inspired neural networks, holds significant value and ***, challenges arise in 3D environments, including excessive turning and vertical movement, as well as the potential for collisions between robots. In response, we propose an improved Glasius Bio-Inspired Neural Network(GBNN) that mitigates decision conflicts among robots and considers the impact of turning and vertical movement on robot decision-making. Furthermore, to address the issue of robots getting trapped in local deadlocks during the search process, we present a dual neural network algorithm based on Levy flights. In the method Dual Glasius Bio-Inspired Neural Network based on Levy Flight(LF-DUAL-GBNN) proposed in this paper, robots obtain random target points through Levy flights and are then guided by a dual neural network to navigate to the vicinity of the target points, thus breaking free from local deadlock states. Finally, we conducted simulation experiments to validate the algorithm's effectiveness. © 2016 IEEE.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：